Instructions to use lschaffer/gemma4-tealkit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lschaffer/gemma4-tealkit with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lschaffer/gemma4-tealkit",
	filename="model-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use lschaffer/gemma4-tealkit with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lschaffer/gemma4-tealkit:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lschaffer/gemma4-tealkit:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lschaffer/gemma4-tealkit:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lschaffer/gemma4-tealkit:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf lschaffer/gemma4-tealkit:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lschaffer/gemma4-tealkit:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf lschaffer/gemma4-tealkit:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lschaffer/gemma4-tealkit:Q4_K_M

Use Docker

docker model run hf.co/lschaffer/gemma4-tealkit:Q4_K_M

LM Studio
Jan

vLLM

How to use lschaffer/gemma4-tealkit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lschaffer/gemma4-tealkit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lschaffer/gemma4-tealkit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lschaffer/gemma4-tealkit:Q4_K_M

Ollama
How to use lschaffer/gemma4-tealkit with Ollama:
```
ollama run hf.co/lschaffer/gemma4-tealkit:Q4_K_M
```

Unsloth Studio new

How to use lschaffer/gemma4-tealkit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lschaffer/gemma4-tealkit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lschaffer/gemma4-tealkit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lschaffer/gemma4-tealkit to start chatting

Docker Model Runner
How to use lschaffer/gemma4-tealkit with Docker Model Runner:
```
docker model run hf.co/lschaffer/gemma4-tealkit:Q4_K_M
```

Lemonade

How to use lschaffer/gemma4-tealkit with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lschaffer/gemma4-tealkit:Q4_K_M

Run and chat with the model

lemonade run user.gemma4-tealkit-Q4_K_M

List all available models

lemonade list

⚠️ This model is purpose-built for the TealKit agentic AI app. It is optimised for MCP tool-call generation inside TealKit's server mode.

Model Details


Base model	google/gemma-4-E2B-it
Fine-tune method	QLoRA (4-bit base, 16-bit adapters, Unsloth)
Quantization	Q4_K_M
GGUF file	`model-q4_k_m.gguf`
Training date	2026-05-15

Quick Start (Ollama)

ollama create gemma4-tealkit -f Modelfile
ollama run gemma4-tealkit

Training Pipeline

QLoRA fine-tuning in Google Colab (Unsloth + TRL), PEFT adapter fusion, llama.cpp GGUF export. See the TealKit training guide.

Downloads last month: 20

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for lschaffer/gemma4-tealkit

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(187)

this model